A Face Recognition Algorithm Robust Against Illumination Variations Using 3-Dimensional Face Shape

The authors propose a face recognition algorithm robust against the illumination variations, using an average face shape. The objective of this paper is two-fold: (1) to propose a new algorithm to estimate one of the illumination-invariant features, i.e., the surface reflectance from single appearance image, and (2) to apply this algorithm to images with various illumination conditions. In (11, we take advantage of the average face shape for local area of face so as to suppress the deviation of shape from the individual one. The correct recognition rate (97.0%) for images of 41 persons with 5 illumination conditions was much higher than that by the edge-based matching method (82.9%).